Yandex Cloud incident

Problems with virtual disks in the ru-central1-b zone

Major Resolved View vendor source →

Yandex Cloud experienced a major incident on September 16, 2024 affecting Compute Cloud and ru-central1-b, lasting 5h 10m. The incident has been resolved; the full update timeline is below.

Started
Sep 16, 2024, 07:10 AM UTC
Resolved
Sep 16, 2024, 12:20 PM UTC
Duration
5h 10m
Detected by Pingoru
Sep 16, 2024, 07:10 AM UTC

Affected components

Compute Cloudru-central1-b

Update timeline

  1. investigating Sep 16, 2024, 07:59 AM UTC

    We have noticed problems with network connectivity between resources in the ru-central1-b availability zone. The developers are already aware of the problem and are working on fixing it.

  2. resolved Sep 16, 2024, 12:26 PM UTC

    We no longer record the impact of the incident on users. Network connectivity has been restored.

  3. identified Sep 17, 2024, 09:06 AM UTC

    After the investigation, it was revealed that the root cause of the incident was a short-term degradation of the virtual disk system, which organically led to a drop in the activity of virtual machines and, accordingly, the traffic between them. At the same time, no real degradation of the network connectivity of virtual machines, either within the zone or with other zones, was revealed. The causes of the incident in the disk subsystem are being investigated, and we will report on them later.